Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    احتمال
    -0.07
    ieder
    -0.07
     Bên
    -0.07
    贫困村
    -0.07
    🤧
    -0.07
     Religious
    -0.07
     młodzie
    -0.07
    Pawn
    -0.06
    שיתוף
    -0.06
    颇
    -0.06
    POSITIVE LOGITS
    .tw
    0.08
    写着
    0.07
    (cuda
    0.07
    ('&
    0.07
    (ci
    0.07
    ("&
    0.06
    dbl
    0.06
    XXX
    0.06
     BN
    0.06
     finishing
    0.06
    Act Density 0.001%

    No Known Activations